Glossary

Model Context Protocol — open standard for AI tool integration

**Model Context Protocol (MCP)** is an open standard, initially developed by Anthropic, for connecting AI clients to external data sources and tools. It defines hosts (the AI client), servers (tool providers), transports, and tool surfaces.
Open spec on GitHubInstall MCP server

Why MCP exists

Without it, every AI host (Claude Desktop, Cursor, etc.) needs custom integration code for every external tool. MCP standardises the interface so tools work everywhere.

Architecture

Host (Claude Desktop) ↔ Transport (stdio or HTTP) ↔ Server (GitHub MCP, GenZAgents MCP, filesystem MCP, etc).

Adoption

Claude Desktop, Claude Code, Cursor, Cline, Windsurf, Continue.dev. Growing list of MCP-compatible hosts.

Where to learn more

modelcontextprotocol.io for the spec. Our /mcp page for GenZAgents-specific integration.

Related

MCP server

A server that exposes tools to MCP-compatible hosts (Claude Desktop, Cursor, Cline, Windsurf).

MCP tool

A typed function exposed by an MCP server to AI hosts. Has a schema; can be invoked by the model.

MCP host

An AI tool that connects to MCP servers — Claude Desktop, Cursor, Cline, Windsurf, Continue.dev.

work receipt

A signed JSON record of AI-mediated work. Ed25519 signature over JCS-canonical JSON.

Get the trust layer for your AI work

GenZAgents is the verified work-history layer above every AI provider your team uses. Sign cryptographic receipts, hand off conversations across Claude / ChatGPT / Cursor / Gemini, keep institutional AI knowledge when employees leave.

Join the launch waitlistInstall MCP server

Last reviewed · 2 min read· Open spec· Changelog